• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.608-620
• /
• 2021

Recent deep learning-based face super-resolution (FSR) works showed significant performances by utilizing facial prior knowledge such as facial landmark and dictionary that reflects structural or semantic characteristics of the human face. However, most of these methods require additional processing time and memory. To solve this issue, this paper propose an efficient FSR models using knowledge distillation techniques. The intermediate features of teacher network which contains dictionary information based on major face regions are transferred to the student through adversarial multi-scale features distillation. Experimental results show that the proposed model is superior to other SR methods, and its effectiveness compare to teacher model.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.30-37
• /
• 2021

Recently, 3D contents used in various fields have been attracting people's attention due to the development of virtual reality and augmented reality technology. In order to produce 3D contents, it is necessary to model the objects as vertices. However, high-quality modeling is time-consuming and costly. In order to convert a 2D character into a 3D model, it is necessary to express it as line drawings through feature line extraction. The extraction of consistent line drawings from 2D cartoon cartoons is difficult because the styles and techniques differ depending on the designer who produces them. Therefore, it is necessary to extract the line drawings that show the geometrical characteristics well in 2D cartoon shapes of various styles. This study proposes a method of automatically extracting line drawings. The 2D Cartoon shading image and line drawings are learned by using adversarial network model, which is artificial intelligence technology and outputs 2D cartoon artwork of various styles. Experimental results show the proposed method in this research can be obtained as a result of the line drawings representing the geometric characteristics when a 2D cartoon painting as input.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.5
• /
• pp.265-278
• /
• 2021

When a dangerous event arises for people inside a building and an immediate evacuation is required, it is important that suitable routes have been previously defined. These situations can happen especially when buildings are crowded, making the occupants have a very high vulnerability and can be trapped if they do not evacuate quickly and safely. However, in most cases, routes are considered based just on their proximity or short distance to the exit areas, and evacuation simulations that include more variables are not performed. This work aims to propose a methodology for building's indoor evacuation activities under the premise of processing simulation scenarios in multi-agent environments. In the methodology, importance indexes of simplified and validated geometry data from a BIM (Building Information Modeling) are considered as heuristic input data in a proposed algorithm. The algorithm is based on AP-Theta^* pathfinding and collision avoidance machine learning techniques. It also includes conditioning variables such as the number of people, speed of movement as well as reaction ability of the agents that influence the evacuation times. Moreover, collision avoidance is applied between people or with objects along the route. The simulations using the proposed algorithm are tested in NetLogo for diverse scenarios, showing feasible evacuation routes and calculating evacuation times in a multi-agent environment. The experimental results are obtained by applying the method in a study case and demonstrate the level of effectiveness of the algorithm, and the influence of the conditioning variables analyzed together when performing safe evacuation routes.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.419-428
• /
• 2021

Shadow removal plays a key role for the pre-processing of image processing techniques such as object tracking and detection. With the advances of image recognition based on deep convolution neural networks, researches for shadow removal have been actively conducted. In this paper, we propose a novel method for shadow removal, which utilizes self attention distillation to extract semantic features. The proposed method gradually refines results of shadow detection, which are extracted from each layer of the proposed network, via top-down distillation. Specifically, the training procedure can be efficiently performed by learning the contextual information for shadow removal without shadow masks. Experimental results on various datasets show the effectiveness of the proposed method for shadow removal under real world environments.

• Structural Engineering and Mechanics
• /
• v.78 no.3
• /
• pp.305-317
• /
• 2021

An AMD control system is usually built based on the original model of a target building. As a result, the fact leads a large calculation workload exists. Therefore, the orders of a structural model should be reduced appropriately. Among various model-reduction methods, a suitable reduced-order model is important to high-rise buildings. Meanwhile, a partial structural information is discarded directly in the model-reduction process, which leads to the accuracy reduction of its controller design. In this paper, an optimal technique is selected through comparing several common model-reduction methods. Then, considering the dynamic characteristics of a high-rise building, an improved balanced truncation (BT) method is proposed for establishing its reduced-order model. The abandoned structural information, including natural frequencies, damping ratios and modal information of the original model, is reconsidered. Based on the improved reduced-order model, a new reduced-order controller is designed by a regional pole-placement method. A high-rise building with an AMD system is regarded as an example, in which the energy distribution, the control effects and the control parameters are used as the indexes to analyze the performance of the improved reduced-order controller. To verify its effectiveness, the proposed methodology is also applied to a four-storey experimental frame. The results demonstrate that the new controller has a stable control performance and a relatively short calculation time, which provides good potential for structural vibration control of high-rise buildings.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.6
• /
• pp.84-89
• /
• 2021

In 2017, the Gyeongju earthquake caused many casualties and considerable property damage by overturning and dropping blocks and bricks. Various reinforcement techniques were proposed, but some problems, such as short length or difficult construction, were encountered. Therefore, this study proposes a long-rawlplug screw anchor to improve the existing rawlplug anchor and conducts an experiment to evaluate the pullout strength. Variables in the pullout test were the compressive strength of concrete and the embedded length of the long-rawlplug screw anchor. According to the results, the pullout strength of the long-rawlplug screw anchor increased as the compressive strength of concrete increased, and they were not affected by the embedded length. Rather, it was found that the screw length of the long-rawlplug was important to the pullout strength.

• The Journal of Korean Academy of Orthopedic Manual Physical Therapy
• /
• v.24 no.2
• /
• pp.75-81
• /
• 2018

Background: The purpose of this study was to investigate the effect of various relaxation techniques on various dysfunction problems caused by shortening of the sagittal muscles. Method: The subjects were 44(18 males, 26 females). The subjects were composed of 3 groups. The experimental group consisted of 14 patients with proprioceptive neuromuscular facilitation stretching (PNF) technique, control group A 15 patients with self myofacial release (SMR) ball exercise, and control group B with 15 patients with Sling exercise. After 3 weeks of relaxation on the hamstring muscle, the length of the hamstring muscle before and after the intervention was compared. Results: The results of relaxation exercise of the snake muscles applied to passive PNF group, SMR ball group, and Sling relaxation group are as follows. 1. In the passive PNF group, the muscle length of the hamstring muscle was significantly increased after the intervention. 2. The muscle length of the hamstring muscle was significantly increased after the intervention in the SMR ball group. 3. Sling relaxation group significantly increased the muscle length of the hamstring muscle after sling exercise intervention. 4. Passive PNF group showed the greatest change in muscle length before and after intervention than SMR ball group and Sling relaxation group. Conclusion: Passive PNF relaxation therapy, SMR ball relaxation therapy, and Sling relaxation therapy applied to the hamstring muscle were effective in increasing muscle length of the hamstring muscle. PNF relaxation therapy showed the most significant effect after 3 weeks intervention.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.91-97
• /
• 2018

The plant factory represents one of the future agricultural systems into which ubiquitous information technology (U-IT) is incorporated, including sensor networking, and helps minimize the influence of external experimental factors that constrain the use of existing greenhouse cultivation techniques. A plant factory's automated cultivation system does not merely provide convenience for crop cultivation, but also expandability as a platform that helps build a knowledge database based on its acquired information and develop education and other application services using the database. For the expansion of plant factory services, this study designed a plant factory interworking service (PFIS) which allows plant factories to share crop growth-related information efficiently among them and performed a test on the service and its implementation.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1463-1474
• /
• 2018

Fuzzing is one of the software testing techniques that find security flaws by inputting invalid values or arbitrary values into the program and various methods have been suggested to increase the efficiency of such fuzzing. In this paper, focusing on the existence of field with high relevance to coverage and software crash, we propose a new method for intensively fuzzing corresponding field part while performing field based fuzzing. In this case, we use a deep learning model called Variational Autoencoder(VAE) to learn the statistical characteristic of input values measured in high coverage and it showed that the coverage of the regenerated files are uniformly higher than that of simple variation. It also showed that new crash could be found by learning the statistical characteristic of the files in which the crash occurred and applying the dropout during the regeneration. Experimental results showed that the coverage is about 10% higher than the files in the queue of the AFL fuzzing tool and in the Hwpviewer binary, we found two new crashes using two crashes that found at the initial fuzzing phase.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.6
• /
• pp.682-689
• /
• 2019

In part-based image representation, the partial shapes of an object are represented as basis vectors, and an image is decomposed as a linear combination of basis vectors where the coefficients of those basis vectors represent the partial (or local) feature of an object. In this paper, a face recognition for occluded faces is proposed in which face images are represented using non-negative matrix factorization(NMF), one of part-based representation techniques, and recognized using an artificial neural network technique. Standard NMF, projected gradient NMF and orthogonal NMF were used in part-based representation of face images, and their performances were compared. Learning vector quantizer were used in the recognizer where Euclidean distance was used as the distance measure. Experimental results show that proposed recognition is more robust than the conventional face recognition for the occluded faces.